Methods, devices, and computer program products for model adaptation
Embodiments of the present disclosure provide methods, devices, and computer program products for model adaptation. The method for model adaptation comprises: receiving, at a first computing device, a data set to be analyzed from a data collector and determining abnormality of the data set to be analyzed using a machine learning model deployed at the first computing device. The method further comprises transmitting, based on the determined abnormality of the data set, at least a portion of data in the data set to a second computing device, for update of the machine learning model, the second computing device having a higher computing capability than the first computing device. The method further comprises obtaining redeployment of the updated machine learning model from the second computing device.
1. A method for model adaptation, comprising:
receiving, at a first computing device, a data set to be analyzed from a data collector;
determining abnormality of the data set using a machine learning model deployed at the first computing device;
transmitting, based on the determined abnormality of the data set, at least a portion of data in the data set to a second computing device for update of the machine learning model, the second computing device having a higher computing capability than the first computing device; and
obtaining redeployment of the updated machine learning model from the second computing device;
wherein the first computing device comprises an edge computing node; and
wherein the second computing device comprises a cloud computing device.
2. The method of claim 1 , wherein a communication speed between the first computing device and the data collector is higher than a communication speed between the second computing device and the data collector.
3. The method of claim 1 , wherein transmitting at least a portion of data in the data set to the second computing device comprises:
providing data determined to be normal in the data set to the second computing device.
4. The method of claim 1 , further comprising:
after an indication of the abnormality of the data in the data set is provided, discarding data determined to be abnormal in the data set.
5. The method of claim 1 , wherein the data collector comprises at least one Internet of Things (IoT) device.
6. A method for model adaptation, comprising:
deploying a trained machine learning model to a first computing device, by a second computing device, the machine learning model being configured to determine abnormality of a data set to be analyzed from a data collector, and the second computing device having a higher computing capability than the first computing device;
receiving at least a portion of data in the data set from the first computing device;
updating the machine learning model based on the received portion of data; and
redeploying the updated machine learning model to the first computing device;
wherein the first computing device comprises an edge computing node; and
wherein the second computing device comprises a cloud computing device.
7. The method of claim 6 , wherein receiving at least a portion of data in the data set comprises:
receiving, from the first computing device, at least a portion of data determined to be normal by the machine learning model in the data set.
8. The method of claim 7 , wherein updating the machine learning model comprises:
obtaining a label related to the received portion of data, the label indicating whether the portion of data is normal or abnormal; and
updating the machine learning model based on the received portion of data and the label.
9. The method of claim 6 , wherein a communication speed between the first computing device and the data collector is higher than a communication speed between the second computing device and the data collector.
10. The method of claim 6 , wherein the data collector comprises at least one Internet of Things (IoT) device.
11. An apparatus comprising at least one of a first electronic device and a second electronic device, the first electronic device comprising:
at least one processor; and
at least one memory storing computer program instructions, the at least one memory and the computer program instructions being configured, with the at least one processor, to cause the first electronic device to perform acts comprising:
receiving a data set to be analyzed from a data collector;
determining abnormality of the data set using a machine learning model deployed at the first electronic device;
transmitting, based on the determined abnormality of the data set, at least a portion of data in the data set to a second electronic device for update of the machine learning model, the second electronic device having a higher computing capability than the first electronic device; and
obtaining redeployment of the updated machine learning model from the second electronic device;
wherein the first electronic device comprises an edge computing node; and
wherein the second electronic device comprises a cloud computing device.
12. The apparatus of claim 11 , wherein a communication speed between the first electronic device and the data collector is higher than a communication speed between the second electronic device and the data collector.
13. The apparatus of claim 11 , wherein transmitting at least a portion of data in the data set to the second electronic device comprises:
providing data determined to be normal in the data set to the second electronic device.
14. The apparatus of claim 11 , wherein the acts further comprise:
after an indication of the abnormality of the data in the data set is provided, discarding data determined to be abnormal in the data set.
15. The apparatus of claim 11 , wherein the data collector comprises at least one Internet of Things (IoT) device.
16. The apparatus of claim 11 , wherein the second electronic device comprises:
at least one processor; and
at least one memory storing computer program instructions, the at least one memory and the computer program instructions being configured, with the at least one processor, to cause the second electronic device to perform acts comprising:
deploying the machine learning model to the first electronic device;
receiving at least a portion of data in the data set from the first electronic device;
updating the machine learning model based on the received portion of data; and
redeploying the updated machine learning model to the first electronic device.
17. The apparatus of claim 16 , wherein receiving at least a portion of data in the data set comprises:
receiving, from the first electronic device, at least a portion of data determined to be normal by the machine learning model in the data set.
18. The apparatus of claim 17 , wherein updating the machine learning model comprises:
obtaining a label related to the received portion of data, the label indicating whether the portion of data is normal or abnormal; and
updating the machine learning model based on the received portion of data and the label.
19. A computer program product being tangibly stored on a non-transitory computer-readable medium and comprising computer-executable instructions which, when executed, cause a device to perform the method of claim 1 .
20. A computer program product being tangibly stored on a non-transitory computer-readable medium and comprising computer-executable instructions which, when executed, cause a device to perform the method of claim 6 .